2000 character limit reached
Real-Time FPGA Demonstrator of ANN-Based Equalization for Optical Communications
Published 23 Feb 2024 in eess.SP and cs.LG | (2402.15288v1)
Abstract: In this work, we present a high-throughput field programmable gate array (FPGA) demonstrator of an artificial neural network (ANN)-based equalizer. The equalization is performed and illustrated in real-time for a 30 GBd, two-level pulse amplitude modulation (PAM2) optical communication system.
- F. N. Khan et al., “An optical communication’s perspective on machine learning and its applications,” J. Lightw. Technol., vol. 37, no. 2, pp. 493–516, 2019.
- P. J. Freire et al., “Towards FPGA implementation of neural network-based nonlinearity mitigation equalizers in coherent optical transmission systems,” in Proc. ECOC, 2022.
- N. Kaneda et al., “Fixed-point analysis and FPGA implementation of deep neural network based equalizers for high-speed PON,” J. Lightw. Technol., vol. 40, no. 7, pp. 1972–1980, 2022.
- J. Ney et al., “From algorithm to implementation: Enabling high-throughput CNN-based equalization on FPGA for optical communications,” in Proc. Internat. Conf. on Embedded Comp. Syst.: Architect., Model. and Simul. (SAMOS XXIII), 2023.
- P. Matalla et al., “Hardware comparison of feed-forward clock recovery algorithms for optical communications,” in Proc. OFC, 2021.
- J. Ney et al., “Unsupervised ANN-based equalizer and its trainable FPGA implementation,” in Proc. EuCNC, 2023.
- V. Lauinger et al., “Fully-blind neural network based equalization for severe nonlinear distortions in 112 gbit/s passive optical networks,” arXiv Prepint, 2024. [Online]. Available: https://arxiv.org/abs/2401.09579
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.