End-to-End Learning of OFDM Waveforms with PAPR and ACLR Constraints

TL;DR

This paper introduces a neural network-based end-to-end approach for OFDM waveform design that optimizes PAPR and ACLR constraints, leading to improved information rates over traditional methods.

Contribution

It presents a novel neural network framework for jointly optimizing OFDM transmitter and receiver to control PAPR and ACLR, enhancing performance.

Findings

Achieves higher information rates than tone reservation baseline.

Successfully enforces PAPR and ACLR constraints during training.

Demonstrates the effectiveness of learned waveforms in simulations.

Abstract

Orthogonal frequency-division multiplexing (OFDM) is widely used in modern wireless networks thanks to its efficient handling of multipath environment. However, it suffers from a poor peak-to-average power ratio (PAPR) which requires a large power backoff, degrading the power amplifier (PA) efficiency. In this work, we propose to use a neural network (NN) at the transmitter to learn a high-dimensional modulation scheme allowing to control the PAPR and adjacent channel leakage ratio (ACLR). On the receiver side, a NN-based receiver is implemented to carry out demapping of the transmitted bits. The two NNs operate on top of OFDM, and are jointly optimized in and end-to-end manner using a training algorithm that enforces constraints on the PAPR and ACLR. Simulation results show that the learned waveforms enable higher information rates than a tone reservation baseline, while satisfying predefined PAPR and ACLR targets.