End-to-End Deep Learning of Optical Fiber Communications

TLDR

The study develops an end‑to‑end deep‑learning optical fiber communication system and proposes a training method that yields robust, reconfiguration‑free transceivers, marking the first step toward DL‑based optimization of such systems. The authors model the transmitter, fiber channel, and receiver as a neural network and use deep learning to optimize transmitter and receiver configurations for minimal symbol error rate, employing a training method that yields robust, reconfiguration‑free transceivers across varying link dispersions. End‑to‑end deep learning yields transceivers that achieve bit error rates below the 6.7 % HD‑FEC threshold, 42 Gb/s over 40 km, and outperform conventional IM/DD schemes, with experimental verification.

Abstract

In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applying it to intensity modulation/direct detection (IM/DD) systems and show that we can achieve bit error rates below the 6.7% hard-decision forward error correction (HD-FEC) threshold. We model all componentry of the transmitter and receiver, as well as the fiber channel, and apply deep learning to find transmitter and receiver configurations minimizing the symbol error rate. We propose and verify in simulations a training method that yields robust and flexible transceivers that allow-without reconfiguration-reliable transmission over a large range of link dispersions. The results from end-to-end deep learning are successfully verified for the first time in an experiment. In particular, we achieve information rates of 42 Gb/s below the HD-FEC threshold at distances beyond 40 km. We find that our results outperform conventional IM/DD solutions based on two- and four-level pulse amplitude modulation with feedforward equalization at the receiver. Our study is the first step toward end-to-end deep learning based optimization of optical fiber communication systems.