End-to-end Autoencoder for Superchannel Transceivers with Hardware Impairment

TL;DR

This paper introduces an end-to-end autoencoder approach for superchannel transceivers that effectively mitigates hardware impairments, significantly reducing symbol error rate and guard band requirements.

Contribution

The study presents a novel end-to-end learning framework specifically designed to address hardware impairments in superchannel systems, outperforming traditional schemes.

Findings

Up to 60% reduction in symbol error rate (SER)

Up to 50% reduction in guard band size

Effective hardware impairment mitigation

Abstract

We propose an end-to-end learning-based approach for superchannel systems impaired by non-ideal hardware component. Our system achieves up to 60% SER reduction and up to 50% guard band reduction compared with the considered baseline scheme.