Deep Learning for Frame Error Probability Prediction in BICM-OFDM Systems

TL;DR

This paper introduces a deep learning method to accurately predict frame error probability in BICM-OFDM wireless systems, outperforming traditional metrics and enhancing link throughput.

Contribution

It develops a neural network-based model for FEP prediction from channel states and demonstrates its superiority over existing methods in accuracy and throughput gains.

Findings

Deep neural networks improve FEP prediction accuracy.

The approach outperforms the traditional EESM metric.

Enhanced FEP prediction leads to increased link throughput.

Abstract

In the context of wireless communications, we propose a deep learning approach to learn the mapping from the instantaneous state of a frequency selective fading channel to the corresponding frame error probability (FEP) for an arbitrary set of transmission parameters. We propose an abstract model of a bit interleaved coded modulation (BICM) orthogonal frequency division multiplexing (OFDM) link chain and show that the maximum likelihood (ML) estimator of the model parameters estimates the true FEP distribution. Further, we exploit deep neural networks as a general purpose tool to implement our model and propose a training scheme for which, even while training with the binary frame error events (i.e., ACKs / NACKs), the network outputs converge to the FEP conditioned on the input channel state. We provide simulation results that demonstrate gains in the FEP prediction accuracy with our approach as compared to the traditional effective exponential SIR metric (EESM) approach for a range of channel code rates, and show that these gains can be exploited to increase the link throughput.