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 2 and 4 level pulse amplitude modulation (PAM2/PAM4) with feedforward equalization (FFE) at the receiver. Our study is the first step towards end-to-end deep learning-based optimization of optical fiber communication systems.
Highlights
T HE application of machine learning techniques in communication systems has attracted a lot of attention in recent years [1], [2]
Since chromatic dispersion and nonlinear Kerr effects in the fiber are regarded as the major information rate-limiting factors in modern optical communication systems [6], the application of artificial neural networks (ANNs), known as universal function approximators [7], for channel equalization has been of great research interest [8]–[12]
The digital-to-analog converters (DACs) and analog-todigital converters (ADCs) components introduce additional quantization noise due to their limited resolution. We model this noise nDAC(t) and nADC(t) as additive, uniformly distributed noise with variance determined by the effective number of bits (ENOB) of the device [27]
Summary
T HE application of machine learning techniques in communication systems has attracted a lot of attention in recent years [1], [2]. Since chromatic dispersion and nonlinear Kerr effects in the fiber are regarded as the major information rate-limiting factors in modern optical communication systems [6], the application of artificial neural networks (ANNs), known as universal function approximators [7], for channel equalization has been of great research interest [8]–[12]. A multi-layer ANN architecture, which enables deep learning techniques [13], has been recently considered in [14] for the realization of low-complexity nonlinearity compensation by digital backpropagation (DBP) [15]. Deep learning has been considered for short-reach communications. For short reaches (1.5 km), BER improvements over common feed-forward linear equalization were achieved
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
