PAPR Reduction in OFDM Systems Using Neural Networks: A Case Study on the Importance of Dataset Generalization

TL;DR

This paper evaluates a neural network designed for PAPR reduction in OFDM systems, emphasizing the importance of dataset generalization to ensure robustness across diverse scenarios.

Contribution

It extends previous work by conducting generalization tests, demonstrating the neural network's effectiveness and robustness in unseen data conditions.

Findings

Neural network maintains PAPR reduction on unseen data.

Model achieves lower computational cost while preserving performance.

Initial conclusions about effectiveness remain valid after generalization tests.

Abstract

In [1], we introduced a NN designed to reduce the PAPR in OFDM systems. However, the original study did not include explicit generalization tests to assess how well the NN would perform on previously unseen data, which prevented a comprehensive evaluation of the model's robustness and applicability in diverse scenarios. To address this gap, we conducted additional generalization assessments, the results of which are presented in this case study. These results serve both to complement and to refine the original analysis reported in [1]. Most importantly, the overall conclusions of the initial study remain valid: the NN is still able to reduce the PAPR level to a desired reference value, also with a lower computational cost, confirming the effectiveness and practical applicability of the proposed method across a more generalized setting.